---
title: "Grundstückspreise in Wien"
output: 
  flexdashboard::flex_dashboard:
    storyboard: true
    css: css/theme_custom.css
    social: menu
    source_code: embed

---



```{r setup, include=FALSE}
library(flexdashboard)
library(here)
library(tidyverse)
library(skimr)
library(janitor)
library(lubridate)
library(rvest)
library(scales)
library(plotly)

district_area_mapping <-  read_html("https://de.wikipedia.org/wiki/Wiener_Katastralgemeinden") %>% 
  html_node(xpath = '//*[@id="mw-content-text"]/div[1]/table') %>% 
  html_table() %>% 
  clean_names()

data <- read_csv2(
    here("01_data", "kaufpreissammlung_liegenschaften.csv"),
    locale = readr::locale(encoding = "latin1")
  ) %>%  clean_names() %>% 
  left_join(select(district_area_mapping, katastral_gemeinde, bezirk),
            by = c("katastralgemeinde" = "katastral_gemeinde")) %>% 
  mutate(erwerbsdatum = dmy(erwerbsdatum),
         jahr = year(erwerbsdatum),
         jahr = if_else(jahr == 2106, 2016, jahr),
         plz = as.factor(plz),
         ez = as.factor(ez) ,
         bezirk = str_extract(bezirk, "\\d{1,2}\\.\\s.+?(?=\\d)"),
         verauserer = case_when(verausserer_code %in% c(1, 2, 4, 5, 6, 7, 10, 11, 12, 14) ~ "Gebietskörperschaften, jur. Personen mit öffentlichem Charakter",
                                verausserer_code == 3 ~ "Gemeinnützige Bauvereinigungen",
                                verausserer_code == 8 ~ "Jur. Personen des Privatrechts",
                                verausserer_code == 9 ~ "Privatpersonen",
                                TRUE ~ "Sonstige"
                                ),
         erwerber  = case_when(erwerbercode %in% c(1, 2, 4, 5, 6, 7, 10, 11, 12, 14) ~ "Gebietskörperschaften, jur. Personen mit öffentlichem Charakter",
                                erwerbercode == 3 ~ "Gemeinnützige Bauvereinigungen",
                                erwerbercode == 8 ~ "Jur. Personen des Privatrechts",
                                erwerbercode == 9 ~ "Privatpersonen",
                                TRUE ~ "Sonstige"
                                ),
         rel_kaufpreis = kaufpreis / gst_fl
         ) %>% 
  filter(
    str_detect(plz, "\\d{4}"),
    between(jahr, 1987, 2019),
    !is.na(bezirk),
    erwerber != "Sonstige",
    verauserer != "Sonstige"
  )

theme_set(theme_bw() + theme(strip.background = element_blank()))
```

### Verteilung Erwerber pro Bezirk

```{r}
erwbars <- data %>% 
  count(bezirk, erwerber, sort = TRUE) %>% 
  group_by(bezirk) %>% 
  mutate(prop = n / sum(n)) %>% 
  ggplot(aes(x = erwerber, y = prop, fill = erwerber)) +
  geom_col() +
  facet_wrap(~ bezirk) +
  scale_y_continuous(labels = percent_format()) +
  scale_fill_manual(values = c("#8FB9A8", "#FEFAD4", "#F1828D", "#765D69")) +
theme(axis.title.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.text.x = element_blank(),
      legend.position = "none",
        strip.background = element_blank(),
      panel.grid.major.x = element_blank(),
      panel.grid.minor.x = element_blank()) +
  labs(y = "Anteil", fill = "Erwerber")

ggplotly(erwbars)
```

### Verteilung der Veräußerer pro Bezirk

```{r}
verau_bars <- data %>% 
  count(bezirk, verauserer, sort = TRUE) %>% 
  group_by(bezirk) %>% 
  mutate(prop = n / sum(n)) %>% 
  ggplot(aes(x = verauserer, y = prop, fill = verauserer)) +
  geom_col() +
  facet_wrap(~ bezirk) +
  scale_y_continuous(labels = percent_format()) +
  scale_fill_manual(values = c("#8FB9A8", "#FEFAD4", "#F1828D", "#765D69")) +
theme(axis.title.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.text.x = element_blank(),
        strip.background = element_blank(),
      panel.grid.major.x = element_blank(),
      panel.grid.minor.x = element_blank()) +
  labs(y = "Anteil", fill = "Veräußerer")

ggplotly(verau_bars)
```


### Chart C

```{r}

```

-----------------------------------------------------------------------

### Chart D

```{r}

```

-----------------------------------------------------------------------

### Chart E

```{r}

```